© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 41572
    Prev
    Next
    INDEX
    Explanations

    Text fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çĺ¤
    -0.31
    çľ¼çľĭ
    -0.27
     Blazers
    -0.27
    污æŁĵ
    -0.26
    大åħ¨
    -0.25
    èĨĿ
    -0.25
    æ£ĭ
    -0.25
    åħ¨éķĩ
    -0.24
     morally
    -0.24
    vfs
    -0.24
    POSITIVE LOGITS
    hecy
    0.28
    oki
    0.28
    tom
    0.27
    çļĦç»ıéªĮ
    0.26
    .ht
    0.25
    .tel
    0.25
    _tl
    0.25
    -secret
    0.24
     expect
    0.24
    itu
    0.24
    Activations Density 0.635%

    No Known Activations